From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks

May 05, 2020
K L Navaneet, Ansu Mathew, Shashank Kashyap, Wei-Chih Hung, Varun Jampani, R. Venkatesh Babu

* Accepted to CVPR 2020; Codes are available at https://github.com/val-iisc/ssl_3d_recon 

  Access Model/Code and Paper
Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

Apr 09, 2020
Jogendra Nath Kundu, Siddharth Seth, Varun Jampani, Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty

* CVPR 2020 (Oral) 

  Access Model/Code and Paper
Self-Supervised Viewpoint Learning From Image Collections

Apr 03, 2020
Siva Karthik Mustikovela, Varun Jampani, Shalini De Mello, Sifei Liu, Umar Iqbal, Carsten Rother, Jan Kautz

* Accepted at CVPR 20 

  Access Model/Code and Paper
Two-shot Spatially-varying BRDF and Shape Estimation

Apr 01, 2020
Mark Boss, Varun Jampani, Kihwan Kim, Hendrik P. A. Lensch, Jan Kautz


  Access Model/Code and Paper
Self-supervised Single-view 3D Reconstruction via Semantic Consistency

Mar 13, 2020
Xueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang, Jan Kautz

* Codes and other resources will be released at: https://sites.google.com/view/unsup-mesh/home 

  Access Model/Code and Paper
SENSE: a Shared Encoder Network for Scene-flow Estimation

Oct 27, 2019
Huaizu Jiang, Deqing Sun, Varun Jampani, Zhaoyang Lv, Erik Learned-Miller, Jan Kautz

* International Conference on Computer Vision 2019 
* ICCV 2019 Oral 

  Access Model/Code and Paper
Learning Propagation for Arbitrarily-structured Data

Sep 25, 2019
Sifei Liu, Xueting Li, Varun Jampani, Shalini De Mello, Jan Kautz

* ICCV 2019 

  Access Model/Code and Paper
Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Jul 12, 2019
Towaki Takikawa, David Acuna, Varun Jampani, Sanja Fidler

* Project Website: https://nv-tlabs.github.io/GSCNN/ 

  Access Model/Code and Paper
SCOPS: Self-Supervised Co-Part Segmentation

May 03, 2019
Wei-Chih Hung, Varun Jampani, Sifei Liu, Pavlo Molchanov, Ming-Hsuan Yang, Jan Kautz

* Accepted in CVPR 2019. Project page: http://varunjampani.github.io/scops 

  Access Model/Code and Paper
Pixel-Adaptive Convolutional Neural Networks

Apr 10, 2019
Hang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, Jan Kautz

* CVPR 2019. Video introduction: https://youtu.be/gsQZbHuR64o 

  Access Model/Code and Paper
Boosting segmentation with weak supervision from image-to-image translation

Apr 04, 2019
Eugene Vorontsov, Pavlo Molchanov, Wonmin Byeon, Shalini De Mello, Varun Jampani, Ming-Yu Liu, Samuel Kadoury, Jan Kautz


  Access Model/Code and Paper
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Oct 07, 2018
Anurag Ranjan, Varun Jampani, Kihwan Kim, Deqing Sun, Jonas Wulff, Michael J. Black


  Access Model/Code and Paper
Superpixel Sampling Networks

Jul 26, 2018
Varun Jampani, Deqing Sun, Ming-Yu Liu, Ming-Hsuan Yang, Jan Kautz

* ECCV2018. Project URL: https://varunjampani.github.io/ssn/ 

  Access Model/Code and Paper
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation

Jul 13, 2018
Huaizu Jiang, Deqing Sun, Varun Jampani, Ming-Hsuan Yang, Erik Learned-Miller, Jan Kautz

* CVPR 2018 
* CVPR 2018 version with minor revisions and supplementary material included. Project page http://jianghz.me/projects/superslomo 

  Access Model/Code and Paper
SPLATNet: Sparse Lattice Networks for Point Cloud Processing

May 09, 2018
Hang Su, Varun Jampani, Deqing Sun, Subhransu Maji, Evangelos Kalogerakis, Ming-Hsuan Yang, Jan Kautz

* Camera-ready, accepted to CVPR 2018 (oral); project website: http://vis-www.cs.umass.edu/splatnet/ 

  Access Model/Code and Paper
Switchable Temporal Propagation Network

May 04, 2018
Sifei Liu, Guangyu Zhong, Shalini De Mello, Jinwei Gu, Varun Jampani, Ming-Hsuan Yang, Jan Kautz


  Access Model/Code and Paper
Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization

Apr 23, 2018
Jonathan Tremblay, Aayush Prakash, David Acuna, Mark Brophy, Varun Jampani, Cem Anil, Thang To, Eric Cameracci, Shaad Boochoon, Stan Birchfield

* CVPR 2018 Workshop on Autonomous Driving 

  Access Model/Code and Paper
On the Integration of Optical Flow and Action Recognition

Dec 22, 2017
Laura Sevilla-Lara, Yiyi Liao, Fatma Guney, Varun Jampani, Andreas Geiger, Michael J. Black


  Access Model/Code and Paper
Semantic Video CNNs through Representation Warping

Aug 10, 2017
Raghudeep Gadde, Varun Jampani, Peter V. Gehler

* ICCV 2017 

  Access Model/Code and Paper
Video Propagation Networks

Apr 11, 2017
Varun Jampani, Raghudeep Gadde, Peter V. Gehler

* Appearing in Computer Vision and Pattern Recognition, 2017 (CVPR'17) 

  Access Model/Code and Paper
Superpixel Convolutional Networks using Bilateral Inceptions

Aug 08, 2016
Raghudeep Gadde, Varun Jampani, Martin Kiefel, Daniel Kappler, Peter V. Gehler

* European Conference on Computer Vision (ECCV), 2016 

  Access Model/Code and Paper
Efficient 2D and 3D Facade Segmentation using Auto-Context

Jun 21, 2016
Raghudeep Gadde, Varun Jampani, Renaud Marlet, Peter V. Gehler

* 8 pages 

  Access Model/Code and Paper
Optical Flow with Semantic Segmentation and Localized Layers

Apr 11, 2016
Laura Sevilla-Lara, Deqing Sun, Varun Jampani, Michael J. Black


  Access Model/Code and Paper
Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Nov 25, 2015
Varun Jampani, Martin Kiefel, Peter V. Gehler


  Access Model/Code and Paper
Permutohedral Lattice CNNs

May 03, 2015
Martin Kiefel, Varun Jampani, Peter V. Gehler


  Access Model/Code and Paper
The Informed Sampler: A Discriminative Approach to Bayesian Inference in Generative Computer Vision Models

Mar 07, 2015
Varun Jampani, Sebastian Nowozin, Matthew Loper, Peter V. Gehler

* Appearing in Computer Vision and Image Understanding Journal (Special Issue on Generative Models in Computer Vision) 

  Access Model/Code and Paper
Consensus Message Passing for Layered Graphical Models

Jan 26, 2015
Varun Jampani, S. M. Ali Eslami, Daniel Tarlow, Pushmeet Kohli, John Winn

* Appearing in Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS) 2015 

  Access Model/Code and Paper